Benen

Agentic Tinkerer | GTM Architect

[Benen @bendoesai]

@ryanair disgusted with your process and issues with online app. Checked in last night, received confirmation via the app. Get to the airport to be told I’ve not checked in and was charged for a late check in.

[Benen @bendoesai]

@ClaudeDevs Always at the time my plan week resets🫪

[Benen @bendoesai]

Anthropic always be resetting weekly limits the day before my usage normally resets

[Benen @bendoesai]

@AnthropicAI Fuck sake….

[Benen @bendoesai]

@iatnon @ClaudeDevs My usage has been taking a battering since opus 4.8 launched. Praying a fix comes soon🙏🏼

[Antoni @iatnon]

I'm actually devistated...

What am I supposed to do the rest of the week?!?!

Only half way through this week and ran out of weekly limits.

CLAUDE WHAT HAVE YOU DONE!?!

Never even came close to weekly limits before @ClaudeDevs please fix this!

[Benen @bendoesai]

Dang, Opus 4.8 is burning through my usage.

One prompt, 21% of usage.

[ClaudeDevs @ClaudeDevs]

New in Claude Code (research preview): dynamic workflows.

Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks.

Use the word "workflow" in a prompt to get started.

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[Benen @bendoesai]

Anthropic seems to have reset everyone's usage... could Opus 4.8 be coming this week?

[Movez @0xMovez]

Spotify's Chief Architect just showed how they ship 4,5K deployments /day with Claude at Anthropic stage

27-minutes. free. By #1 music app dev

"More than 99% of our engineers use AI coding tools. Adoption took off after Opus 4.5"

Worth more than any $500 vibe-coding course.

[Benen @bendoesai]

@KaiXCreator

[Claude @claudeai]

Next stop: London.

Register to tune in tomorrow for deep dives, demos, and conversations with the teams behind Claude: https://t.co/6le4bIXvJt

[Benen @bendoesai]

@benswerd Resizing the terminal window has been fixing it for me…

[Benen @bendoesai]

@Kekius_Sage Are we cooked?

[Benen @bendoesai]

@nalinrajput23 This & shiny keys

[Benen @bendoesai]

@pcshipp More than one electron app and you’re going to struggle🥲

[Benen @bendoesai]

Bigger context isn't a free lunch.

A million-token window plus an 'extreme' mode means more compute, latency, and cost.

Be honest: do you need whole-book context or smarter retrieval and tests?

Try chunking, retrieval-augmented prompts, and trace-driven evaluations first.

Would you pay for attention or for a headline?

[Benen @bendoesai]

@lukecodez Would have gone hard in 2006

[Benen @bendoesai]

Stop guessing why your AI agent failed.

LangWatch gives traces, simulators, and an LLM judge so you can run full scenarios.

Turn failing traces into test cases and version prompts like code with GitOps.

Ship agents that don't explode in production.

Want the checklist for safe agent launches?